scholarly journals Hybrid recognition for one stroke style cursive handwriting characters

Author(s):  
Teng Long ◽  
Lian-Wen Jin
Keyword(s):  
1979 ◽  
Vol 11 (3) ◽  
pp. 145-154 ◽  
Author(s):  
J. Duvernoy ◽  
D. Charraut
Keyword(s):  

1987 ◽  
Vol PAMI-9 (5) ◽  
pp. 715-722 ◽  
Author(s):  
Hussein Almuallim ◽  
Shoichiro Yamaguchi
Keyword(s):  

2015 ◽  
Author(s):  
Brian L. Davis ◽  
William A. Barrett ◽  
Scott D. Swingle
Keyword(s):  

2021 ◽  
Author(s):  
Channa Li

In this paper, I focus on the palaeography of a collection of eight Tibetan manuscripts hypothesised to have been written by the same scribal hand. The eight manuscripts—IOL Tib J 217, IOL Tib J 686, IOL Tib J 687, IOL Tib J 625, IOL Tib J 588, IOL Tib J 619, P. T. 770, and P. T. 783v—are closely related, not merely in light of their sophisticated cursive handwriting, but also by virtue of their common textual genre (being summaries or commentaries rather than direct scriptural translations) and thematic content: these Tibetan texts were all based on Chinese sources and attributed to Gö Chödrup (fl. first half of the 9th c., Tib. ’Gos Chos grub, Chin. Wu Facheng 吳法成), either directly or indirectly. Moreover, many manuscripts produced by the imperial Tibetan copying project contain editorial records written in the same hand; these records indicate that Chödrup acted as the final proofreader. Therefore, we can now more confidently attribute this hand to Chödrup himself. By establishing a typology of this handwriting and offering a table of how syllables are written by this hand in the appendix, this paper contributes to a better reading of manuscripts containing this type of script and can potentially provide a benchmark for further recognition of works written in the same hand.


Author(s):  
RAMIN HALAVATI ◽  
SAEED BAGHERI SHOURAKI

Persian is a fully cursive handwriting in which each character may take different forms in different parts of the word, characters overlap and there is a wide range of possible styles. These complexities make automatic recognition of Persian a very hard task. This paper presents a novel approach on recognition of such writings systems which is based on the description of input stream by a sequence of fuzzy linguistic terms; representation of character patterns with the same descriptive language; and comparison of inputs with character patterns using a novel elastic pattern matching approach. As there is no general benchmark for recognition of Persian handwriting, the approach has been tested on the set of words in first primary Iranian school books including 1250 words resulting in 78% correct recognition without dictionary and 96% with dictionary.


Sign in / Sign up

Export Citation Format

Share Document